Publications by authors named "Seungpyo Kang"
Article Synopsis
- Protein aggregation is a key factor in Alzheimer's and Parkinson's diseases, with recent research emphasizing the importance of aggregation-prone regions and β-strand interactions.* -
- This study develops a Graph Convolutional Network (GCN) using an enhanced dataset from the Protein Data Bank and AlphaFold2.0 to predict protein aggregation scores, achieving a high accuracy (R² = 0.9849) and low error rate (MAE = 0.0381).* -
- The active learning process within the GCN identified 99% of proteins prone to aggregation while only searching 29% of the data, highlighting the model's efficiency and potential for aiding disease diagnosis and treatment.*
Article Synopsis
- The study focuses on the growing significance of atomic layer deposition (ALD) technology in semiconductor device miniaturization, highlighting the need for low-melting-point precursors for efficient processing.
- Researchers created a comprehensive database containing melting point data for 1,845 organic metal compounds (OMCs), including important structural information, by extracting data from chemical vendor sources and scientific papers using natural language processing.
- The developed database aims to facilitate quicker and more cost-effective identification of suitable ALD precursors, which is essential for advancing the semiconductor industry, despite the moderate performance of a neural network model used for melting point predictions.
Prediction of Protein Aggregation Propensity via Data-Driven Approaches.
ACS Biomater Sci Eng
November 2023
Protein aggregation occurs when misfolded or unfolded proteins physically bind together and can promote the development of various amyloid diseases. This study aimed to construct surrogate models for predicting protein aggregation via data-driven methods using two types of databases. First, an aggregation propensity score database was constructed by calculating the scores for protein structures in the Protein Data Bank using Aggrescan3D 2.
View Article and Find Full Text PDFScreening Platform for Promising Na Superionic Conductors for Na-Ion Solid-State Electrolytes.
ACS Appl Mater Interfaces
September 2023
Na-ion batteries are considered a promising alternative to the analogous Li-ion batteries because of their low manufacturing cost, large abundance, and similar chemical/electrochemical properties. In particular, research on Na-ion solid electrolytes, which resolve the flammability issues associated with liquid electrolytes and increase the energy density obtained using a particular metal anode, is rapidly growing. However, the ionic conductivities of these materials are lower than those of liquids.
View Article and Find Full Text PDFAccelerated Discovery of Novel Garnet-Type Solid-State Electrolyte Candidates via Machine Learning.
ACS Appl Mater Interfaces
February 2023
All-solid-state batteries (ASSBs) have attracted considerable attention because of their higher energy density and stability than conventional lithium-ion batteries (LIBs). For the development of promising ASSBs, solid-state electrolytes (SSEs) are essential to achieve structural integrity. Thus, in this study, a machine-learning-based surrogate model was developed to search for ideal garnet-type SSE candidates.
View Article and Find Full Text PDF